artemka081
Machine Learnung Engineer
My technical stack:
- Python: NumPy, Pandas, Scikit-learn, CatBoost, XGBoost, LightGBM, PyTorch, HuggingFace, transformers, LangChain.
- Data Visualization: Matplotlib, seaborn, Plotly, Dash.
- NLP: NLTK, SpaCy, Gensim, Fine-Tuning LLM, LoRA, Prompt Engineering, OpenAI API, llama.cpp.
- MLOps: Linux/Unix, Bash, Docker, Git, MLflow, FastAPI.
- Databases: SQL (PostgreSQL, ClickHouse), NoSQL (MongoDB), Redis, Neo4j.
- Programming: Asynchronous programming, OOP, design patterns, multiprocessing.
Outside of work, I continue exploring technologies:
- I run a blog about artificial intelligence and its impact on our lives: link
- I participate in discussions on Habr and occasionally publish articles there myself.
- I often attend conferences and meetups (for example, I gave a talk at Data Fest 2024: link
- I love testing new gadgets and software, especially if they involve AI.
- My sport is Data Science competitions. I enjoy solving Kaggle challenges and participating in hackathons. Recently, I took part in the "LMSYS — Chatbot Arena Human Preference Predictions" competition on Kaggle. Currently, I am working on the "VK RecSys Challenge."
And also:
- I have been into film photography for a couple of years and have built a small collection of Soviet cameras.
- I am a Dungeon Master. I enjoy tabletop role-playing games and host adventures for friends and colleagues on weekends. My favorite class in D&D is Paladin.
- I love automating and measuring everything. I am passionate about personal productivity, maintaining a knowledge base in Obsidian.
- I ride a mountain bike through forest trails.
Experience: 4 years
Yearly salary: $62,000
Hourly rate: $45
Nationality: 🌏 Remote
Residency: 🌏 Remote
Experience
AI-Researcher
OCRV 2022 - 2024
- Developed a predictive model for railway infrastructure failures (F1 = 0.84, critical incident recall = 0.91) with high interpretability using SHAP, LIME, and Feature Importance. - Implemented the Talk2Model system to explain predictions in natural language. - Replaced the Word2Vec model with RoBERTa, improving clustering accuracy in an employee churn prediction project. - Accelerated ML models by introducing a feature selection system based on NSGA-II and bio-inspired algorithms. - Designed an anomaly detection system for IT monitoring data to predict service failures. - Initiated the integration of MLflow to ensure logging and reproducibility of team experiments. - Conducted onboarding and mentorship for interns, training them in ML fundamentals and model interpretability. Stack: Python, CatBoost, XGBoost, Scikit-Learn, PyTorch, DEAP, Pymoo, SHAP, LIME, Alibi Explain, MLflow, ClickHouse, Docker, GitLab
ML-Engineer
Freelance 2020 - 2024
- Developed backends for web applications using Python Django, FastAPI, and Flask. - Created a Telegram bot with AIOgram, leveraging LLM and LangChain for analyzing RSS news feeds, generating recommendations for authors, and selecting relevant content. - Trained an LSTM neural network to detect text generated by LLMs (F1 = 0.62). - Implemented a RAG system for managing a personal knowledge base using LLama3, Chroma, and LangChain. - Conducted research on applying multi-objective optimization algorithms to create an ideal cryptocurrency portfolio. Stack: Python, Django, FastAPI, RabbitMQ, Keras, LangChain, Chroma, AIOgram, PostgreSQL, SQLAlchemy, Docker, GitHub
Skills
ai
big-data
blockchain
data-science
nosql
python
pytorch
sql
english
german
russian